Semi-automated identification of biological control agent using artificial intelligence.

The accurate identification of biological control agents is necessary for monitoring and preventing contamination in integrated pest management (IPM); however, this is difficult for non-taxonomists to achieve in the field. Many machine learning techniques have been developed for multiple applications (e.g., identification of biological organisms). Some phytoseiids are biological control agents for small pests, such as Neoseiulus barkeri Hughes. To identify a precise biological control agent, a boosting machine learning classification, namely eXtreme Gradient Boosting (XGBoost), was introduced in this study for the semi-automated identification of phytoseiid mites. XGBoost analyses were based on 22 quantitative morphological features among 512 specimens of N. barkeri and related phytoseiid species. These features were extracted manually from photomicrograph of mites and included dorsal and ventrianal shield lengths, setal lengths, and length and width of spermatheca. The results revealed 100% accuracy rating, and seta j4 achieved significant discrimination among specimens. The present study provides a path through which skills and experiences can be transferred between experts and non-experts. This can serve as a foundation for future studies on the automated identification of biological control agents for IPM.

Laser-Scanned Programmable Color Temperature of Electroluminescence from White Light-Emitting Electrochemical Cells.

Recently, the control of correlated color temperature (CCT) of artificial solid-state white-light sources starts to attract more attention since CTs affect human physiology and health profoundly. In this work, we proposed and demonstrated a method that can widely tune the CCTs of electroluminescence (EL) from white-light-emitting electrochemical cells (LECs) by employing plasmonic filters. These integrated on-chip plasmonic filters are composed of semicontinuous thin Ag film or Ag nanoparticles (NPs) both included in the indium tin oxide anode contact, which have different characteristics of plasmonic resonant absorptions that can tune the EL spectra of white LECs. The CCTs of EL from white LECs integrated with semicontinuous thin Ag film and randomly distributed Ag NPs are 5778 and 2350 K, respectively. A commercially available laser scanning system was used to locally thermal anneal the semicontinuous thin Ag film to form the randomly distributed Ag NPs on the scanned areas. Hence, these two kinds of filters can be integrated on the same chip of white LEC, giving more freedom to control the CCTs of white EL and more potential applications. In addition, the laser scanning system used here is quite often used in display manufactures so that our proposed method can be immediately adopted by the light-emitting diode industry.

Caregiver's needs as predictors of hospital readmission for the elderly in Taiwan.

The problems of caregivers are identified as one of the major causes, as well as a preventable one, for the unplanned hospital readmissions of elderly patients. Family caregivers are found to be under intense stress and burden, and to encounter many difficulties preparing themselves, both physically and mentally, for the return home from the hospital of an elderly family member. However, few studies of rehospitalization of the elderly have focused on the point of view of the family caregiver. The purpose of this study was to explore the predictors, especially the needs of the family caregiver, for rehospitalization, within a month after having been discharged, for elderly patients in Taiwan. A prospective, descriptive and correlational study, using 216 elderly patients and their family caregivers from the internal medicine wards of a medical center in Northern Taiwan was conducted. It was found that elderly patients with caregivers requesting help from a support group were 5.3 times more likely to be rehospitalized than those with caregivers that did not request such help. In addition, the odds of rehospitalization for elderly patients with some self-care ability, whose caregiver reported at least one need for social services, was 9.03 (CI=2.32-35.16) times that of those whose caregivers reported no need for social services. Based on the findings of this study, health care providers need to assess the self-care ability of their elderly patients. In addition they should assess the need for support groups and social services to caregivers before the hospital discharge of Taiwanese elders, and perhaps other Chinese populations as well.

Predictors of nursing home placement and home nursing services utilization by elderly patients after hospital discharge in Taiwan.

BACKGROUND: Providing appropriate follow-up health/long-term care services after hospital discharge for elderly persons is important to enhance health and quality of life. Therefore, identifying factors that affect follow-up service utilization has become an important concern. Most studies of predictors of follow-up service utilization for elderly persons after discharge were conducted in the United States of America (USA). Taiwan differs substantially from the USA in health care system, clinical practice, case-mix, culture, and social organization; thus the findings from the USA need to be validated in Taiwan to ensure appropriate discharge referrals. AIM: To investigate pre-discharge predictors of follow-up care including home nursing services and nursing home placement for elderly patients, discharged from hospitals in Taiwan. METHODS: A prospective study with a case-control design was used. FINDINGS: The strongest predictors of institutionalization in a nursing home at 1, 3 and 6 months after discharge were the elderly person's pre-admission institutionalization (0.33 to 0.48) and the caregiver's preference for institutional displacement (0.23 to 0.85). The strongest predictors of use of home nursing services were the elder's self-care ability (0.69 to 0.76), conscious level (0.51 to 0.73), and tubes remaining before discharge (0.58 to 0.79). These predictors were stable at 1, 3 and 6 months after discharge and could correctly classify 60-89% of sample. CONCLUSIONS: When taking nursing home and home nursing utilization into considerations at the same time, the elderly person's pre-admission institutionalization and the caregiver's preference for institutional displacement strongly predicted nursing home utilization after hospital discharge. The elder's self-care ability, conscious level, and tubes remaining before discharge strongly predicted the use of home nursing services after discharge.